A new policy for contextual bandits adapts to reward vector shifts.
problem Learning under reward vector shifts with ordered rewards.
method Adaptive-discretization and optimistic elimination policy.
result Established upper bounds on preference-based regret.
Proposes MRO to achieve uniformly low regret in distributionally robust learning.
problem Learning under unknown test distributions (distribution shift).
method Minimax Regret Optimization (MRO) for robust machine learning.
result MRO achieves uniformly low regret across all test distributions.
Algorithm minimizes regret in predictive models influenced by their own predictions.
problem Finding near-optimal models under performativity with unknown shifts.
method Developed an algorithm that uses performative feedback to achieve low regret, scaling only with distribution shift complexity.
result Achieved regret bounds scaling with distribution shift complexity, not reward function complexity.
New method reduces regret in nonparametric bandits with unknown covariate shifts.
problem Optimal actions depend on context, but context distributions can change over time.
method Derives new regret bounds for nonparametric bandits under covariate shifts.
result Regret bounds adaptively attainable without knowledge of shift time or magnitude.
Optimal learning rate schedules for SGD in changing data distributions.
problem Minimizing regret in online learning with changing data distributions.
method Characterized optimal schedules for linear regression, proposed schedules for general convex and non-convex losses, and defined a notion of regret for non-convex losses.
result Upper and lower bounds for regret with constants for convex losses, and an upper bound on total expected regret for non-convex losses.
New algorithm reduces regret from sqrt(T) to polylog(T) in stochastic contextual linear bandits.
problem Achieving logarithmic regret in stochastic contextual linear bandits.
method Low Regret Stochastic Contextual Bandits ( exttt{LR-SCB}) algorithm, exploiting stochastic contexts and parameter estimation.
result Logarithmic regret (polylog(T)) achieved, improving over sqrt(T) lower bound.
Mirror descent with an entropic regularizer is known to achieve shifting regret bounds that are logarithmic in the dimension. This is done using either a carefully designed projection or by a weight sharing technique. Via a novel unified analysis, we show that these two approaches deliver essentially equivalent bounds …
Algorithm adapts to shifting domains with minimal label queries.
problem Adaptive learning in online machine learning systems with domain shifts.
method Adaptive algorithm balancing regret and label queries for hidden domains.
result Achieves lower regret compared to uniform and greedy queries.
This paper improves GP-UCB by using a shifted exponential distribution for confidence parameters.
problem Theoretical confidence parameter in GP-UCB increases with iterations, leading to large values.
method Introduced IRGP-UCB, a randomized variant of GP-UCB using a shifted exponential distribution for confidence parameters.
result IRGP-UCB achieves sub-linear regret without increasing the confidence parameter.
New method tracks shifts in infinite-armed bandits without prior knowledge.
problem Tracking shifts in non-stationary infinite-armed bandits.
method Blackbox conversion of finite-armed MAB to infinite-armed non-stationary, randomized elimination.
result First parameter-free optimal regret bounds for all reservoir regularity regimes.
Paper tackles dynamic label shift in online learning, achieving optimal performance.
problem Adapting to changing class marginals in online supervised and unsupervised learning.
method Develops novel algorithms reducing adaptation to online regression, achieving optimal dynamic regret.
result Achieves superior performance in various online label shift scenarios.
Paper tackles online adaptation to changing label distributions.
problem Adapting machine learning models to changing label distributions in real-world settings.
method Leverages novel analysis to show estimation of expected test loss is possible without true labels. Proposes adaptation algorithms inspired by classical online learning techniques.
result Empirically verified that OGD is particularly effective and robust to various label shift scenarios.
Study on tracking preference shifts in dueling bandits problems.
problem Tracking significant preference shifts in dueling bandits problems.
method Analysis of dueling bandits with distribution shifts, focusing on significant shifts (Suk and Kpotufe, 2022).
result Design of adaptive algorithms with O ( K i l d e L T ) O(\sqrt{K ilde{L}T}) O ( K i l d e L T ) dynamic regret for certain preference distribution classes. New algorithms minimize regret in changing environments for piecewise Lipschitz functions.
problem Optimizing in unpredictable, time-varying conditions for piecewise Lipschitz functions.
method Introduced shifting regret as a metric, and provided bounds for O ( s d T log T + s T 1 − β ) O(\sqrt{sdT\log T}+sT^{1-β}) O ( s d T log T + s T 1 − β ) . result Improved bounds for β β β -dispersed functions, with empirical validation in online clustering. Gradient equilibrium improves online learning performance without requiring sublinear regret.
problem Achieving sublinear regret in online learning.
method Gradient equilibrium: average of gradients converges to zero.
result Gradient equilibrium can be achieved by standard online learning methods.
SAMPLR optimizes for ground truth in aleatoric parameters to avoid curriculum-induced covariate shift.
problem Curriculum learning shifts training distribution, leading to suboptimal policies in aleatoric settings.
method SAMPLR optimizes ground-truth utility function, avoiding curriculum-induced covariate shift.
result SAMPLR preserves optimality under ground-truth distribution, promoting robustness across various environments.
This paper tackles continuous covariate shift by adaptively training predictors.
problem Continuous covariate shift where input distributions change over time.
method Online density ratio estimation method to adaptively train predictors.
result Excess risk guarantee for the predictor through dynamic regret bound.
Learning reward functions can lead to poor policy performance despite low error.
problem Low error in learned reward functions does not guarantee low regret in policy performance.
method Mathematical analysis of reward learning and policy optimization.
result A low expected test error of the reward model guarantees low worst-case regret, but error-regret mismatch can occur with certain data distributions.
Paper tackles online label shift in real-world applications.
problem Adapting to changing label distributions in online learning.
method Formulated an unbiased risk estimator and proposed online ensemble algorithms.
result Achieved optimal dynamic regret, indicating adaptability to label shift.
Memory-limited learning tackles adversarial bandits with reduced storage.
problem Adversarial bandit problem with limited memory storage.
method Hierarchical learning policy with sublinear memory requirement.
result Established sublinear regret bounds for weak and shifting regrets.
New algorithm tracks changes in infinite action space rewards.
problem Non-stationary Lipschitz bandits with infinite actions.
method Adaptive tracking of significant shifts using hierarchical discretization.
result Achieves minimax-optimal dynamic regret bound of O ~ ( i l d e L 1 / 3 T 2 / 3 ) \mathcal{\widetilde{O}}( ilde{L}^{1/3}T^{2/3}) O ( i l d e L 1/3 T 2/3 ) . Paper develops a robust Bayesian optimization method for noisy zeroth-order settings.
problem Achieving robustness to distributional shift in machine learning.
method Distributionally robust Bayesian optimization (DRBO) algorithm for noisy zeroth-order optimization.
result DRBO algorithm provably obtains sub-linear robust regret in various settings.
Algorithm learns from offline data to improve performance in target environment.
problem Learning from offline data in a target environment with unknown shifts.
method Adaptive algorithm that uses offline data to improve performance when informative.
result Algorithm provably improves performance over purely online learning when offline data are informative.
Paper tackles transfer learning for contextual multi-armed bandits under covariate shift.
problem Nonparametric contextual multi-armed bandits with covariate shift.
method Established minimax rate of convergence, proposed transfer learning algorithm.
result Achieved near-optimal statistical guarantees for learning in target domain.
Novel hyperparameter optimization for target tasks under covariate shift.
problem Hyperparameter optimization under multi-source covariate shift.
method Construct variance reduced estimator to unbiasedly approximate target objective; propose no-regret hyperparameter optimization procedure.
result Proposed framework broadens applications of automated hyperparameter optimization.
We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, …
We develop the setting of sequential prediction based on shifting experts and on a "smooth" version of the method of specialized experts. To aggregate experts predictions, we use the AdaHedge algorithm, which is a version of the Hedge algorithm with adaptive learning rate, and extend it by the meta-algorithm Fixed Shar…
Anchor-TS uses median anchoring to improve online decision-making from offline data with distribution shift.
problem Improving online decision-making from offline data with distribution shift.
method Sample-Mean Anchored Thompson Sampling (Anchor-TS) with median anchoring.
result Anchor-TS safely leverages offline data to accelerate online learning and reduces regret.
New method tracks significant shifts in nonparametric bandits.
problem Tracking significant changes in nonparametric contextual bandits.
method Proposed a notion of 'experienced significant shifts' to adapt to minimax rate without knowledge of change parameters.
result Experienced significant shifts count fewer changes than traditional metrics, leading to an adaptive algorithm.
New algorithm reduces bandit regret by graph domination number.
problem Adversarial multi-armed bandit with partial observations and switching costs.
method New algorithm with improved policy regret bounds.
result Regret depends only on the domination number of the feedback graph.
This study develops a dynamic inverse optimization framework to recover hidden, time-varying preferences from observed allocation trajectories.
problem The gap between classical optimization theory and real-world practice, especially in the presence of drift and shocks.
method Dynamic inverse optimization framework using a drift-aware estimator grounded in convex analysis and online learning theory.
result Sharp static and dynamic regret bounds for the framework, demonstrating its responsiveness to gradual drift and sudden shocks.
Algorithm finds best mixture of training datasets for improved validation performance.
problem Learning from mixture distributions with covariate shift.
method Combines SGD with optimistic tree search and model re-use over mixture space.
result Proves simple regret guarantees for recovering optimal mixture.
New method for semiparametric bandits reduces regret to optimal levels.
problem Complex reward structures in semiparametric bandits.
method Experimental-design approach with sharp regret bound and PAC bound.
result Minimax regret of i l d e O ( d T ) ilde{O}(\sqrt{dT}) i l d e O ( d T ) and logarithmic regret under positive suboptimality gap. New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.
problem Uncertainty quantification in online settings with changing data distributions.
method Developed new online conformal prediction methods that minimize strongly adaptive regret.
result Achieve near-optimal strongly adaptive regret and approximately valid coverage.
Adaptive algorithms minimize regret in matching markets with contextual arm preferences.
problem Minimizing regret in matching markets with context-dependent player utilities.
method Developed adaptive algorithms for stochastic and adversarial contexts, providing upper and lower bounds.
result Achieved sublinear regret bounds for both stochastic and adversarial contexts.
OSAMD adapts online to changing distributions with limited labels.
problem Models struggle with continual distribution shifts and expensive labeling in changing environments.
method Online Active Continual Adaptation with OSAMD, an online teacher-student structure and margin-based criterion.
result OSAMD achieves favorable dynamic regret bounds under changing environments with limited labels.
Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.
problem Efficient optimisation of expensive black-box functions in unknown search spaces.
method Expands search space over iterations based on a hyperharmonic series, scales to high dimensions.
result Sub-linear regret growth for both algorithms.
RAVEN-UCB addresses non-stationary MAB problems with tighter regret bounds.
problem Non-stationary environments in multi-armed bandits.
method Combines variance-aware adaptation with three innovations: confidence bounds, adaptive control, and recursive updates.
result Achieves tighter regret bounds than UCB1 and UCB-V.
The paper tackles personalized policy learning from diverse data sources in a federated setting.
problem Learning personalized decision policies from observational bandit feedback across multiple heterogeneous data sources.
method Introduces a novel regret analysis for distinguishing global and local regret, and presents a federated policy learning algorithm using local policies trained with doubly robust offline policy evaluation strategies.
result Establishes finite-sample upper bounds on global and local regret, characterizing them by source heterogeneity and distribution shift.
This paper describes a new online convex optimization method which incorporates a family of candidate dynamical models and establishes novel tracking regret bounds that scale with the comparator's deviation from the best dynamical model in this family. Previous online optimization methods are designed to have a total a…
New algorithms achieve better regret bounds for online classification with relaxed benchmarks.
problem Competing with worst-case optimal binary loss in online classification.
method Comparing against predictors robust to small input perturbations, performing well under Gaussian smoothing, or maintaining a prescribed output margin.
result Regret guarantees depend only on VC dimension and instance space complexity, with an O ( log ( 1 / γ ) ) O(\log(1/γ)) O ( log ( 1/ γ )) dependence on the generalized margin. New method tracks significant arm switches to improve bandit algorithms.
problem Adaptive procedures for bandits with unknown changes in reward distribution.
method Proposes a new notion of significant shift to count severe changes.
result Achieves faster rates than previous methods, especially when few changes are severe.
This work tackles robust Bayesian optimization under data shift using φ-divergences.
problem Bayesian optimization under uncertainty and data shift.
method Distributionally robust optimization with φ-divergences.
result A computationally tractable algorithm with provable sublinear regret bounds.
Optimal algorithm for identifying best-arm with minimal regret.
problem Identifying the best arm in two treatments with limited budget.
method Neyman allocation based on outcome standard deviations.
result Neyman allocation is minimax optimal for simple regret.
FADE adapts machine learning models to evolving data efficiently.
problem Sequential covariate shift in dynamic environments.
method FADE uses Fisher information geometry for robust learning under SCS.
result FADE achieves up to 19% higher accuracy under severe shifts.
Study online conformal prediction for non-stationary data with optimal training-conditional regret.
problem Online prediction for non-stationary data streams with unknown distribution drift.
method Proposes split-conformal and full-conformal algorithms that adapt to drift detection and incorporate stability for online learning.
result Proves minimax-optimal regret for online full conformal algorithm under appropriate restrictions.
New framework shifts bandit algorithms from expected reward to preference metrics, optimizing mixtures of arms.
problem Traditional bandit algorithms focus on expected rewards, ignoring variability and risk.
method Introduces preference metrics (PMs) and designs algorithms to optimize mixtures of arms.
result Optimal policy selects mixtures of arms based on specific weights, not a single best arm.
Algorithm balances learning and coverage for multi-robots over unknown fields.
problem Balancing learning and coverage for multi-robots over unknown, nonuniform sensory fields.
method DSLC algorithm that schedules learning and coverage epochs, using Gaussian Process modeling and coverage regret analysis.
result Upper bound on expected cumulative coverage regret provided for DSLC.